Security audit

宠物友好酒店

Security checks for vulnerabilities and agentic risk

Overview

The skill does not show malicious code or data collection, but it advertises pet-friendly hotel search while mainly implementing pet flight, train, and document lookups.

Install only if you want a local Chinese-language pet travel reference for China-focused airline, rail, and document guidance. Do not rely on it for actual nationwide pet-friendly hotel search or current chain-specific hotel policy; verify hotel, airline, railway, and destination requirements directly before booking or travel.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The skill’s description prominently claims nationwide pet-friendly hotel search and hotel-brand policy lookup, but the declared tools only cover airline, train, and travel-document workflows. This mismatch can mislead users into relying on incomplete or nonexistent hotel-policy functionality, which is risky in a travel/compliance context where incorrect assumptions may disrupt bookings or pet transport plans.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The skill name, description, examples, and all user-facing documentation are entirely in Chinese, which indicates a fixed language/locale experience. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly documented and justified, which it is not here.

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The manifest describes a hotel-focused skill covering pet-friendly hotel stay policies and nationwide hotel search, with travel-policy information as supplementary content. In this file, the documented tools and implemented functions are all about pet flight policy, train policy, and travel documents, while hotel content is only a small static tip block attached to one response rather than a real hotel policy query capability.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This code presents the skill as a China-focused pet travel assistant and all user-facing strings are fixed in Chinese. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Static analysis

No suspicious patterns detected.